Comparison of Quantitative and Qualitative (Q)SAR Models Created for the Prediction of K(i) and IC(50) Values of Antitarget Inhibitors

Estimation of interaction of drug-like compounds with antitargets is important for the assessment of possible toxic effects during drug development. Publicly available online databases provide data on the experimental results of chemical interactions with antitargets, which can be used for the creation of (Q)SAR models. The structures and experimental K(i) and IC(50) values for compounds tested on the inhibition of 30 antitargets from the ChEMBL 20 database were used. Data sets with K(i) and IC(50) values including more than 100 compounds were created for each antitarget. The (Q)SAR models were created by GUSAR software using quantitative neighborhoods of atoms (QNA), multilevel neighborhoods of atoms (MNA) descriptors, and self-consistent regression. The accuracy of (Q)SAR models was validated by the fivefold cross-validation procedure. The balanced accuracy was higher for qualitative SAR models (0.80 and 0.81 for K(i) and IC(50) values, respectively) than for quantitative QSAR models (0.73 and 0.76 for K(i) and IC(50) values, respectively). In most cases, sensitivity was higher for SAR models than for QSAR models, but specificity was higher for QSAR models. The mean R(2) and RMSE were 0.64 and 0.77 for K(i) values and 0.59 and 0.73 for IC(50) values, respectively. The number of compounds falling within the applicability domain was higher for SAR models than for the test sets.